Struct GraphIoProfile 

pub struct GraphIoProfile {
    pub kernel_launches: usize,
    pub sync_points: usize,
    pub host_output_bytes: u64,
    pub device_traffic_bytes: u64,
}

Host-visible traffic and sync points for one forward pass.

Fields

kernel_launches: usize

Kernel / thunk dispatches (one per non-view executable node).

sync_points: usize

GPU flush + host-side thunk boundaries (Metal LogMel, host FFT fallback, …).

host_output_bytes: u64

Bytes returned to the caller via graph outputs (CompiledGraph::run).

device_traffic_bytes: u64

Bytes moved inside the device arena (read inputs + write outputs per node).

Implementations

impl GraphIoProfile

pub fn host_readback_bytes(&self, unified_memory: bool) -> u64

Trait Implementations

impl Clone for GraphIoProfile

fn clone(&self) -> GraphIoProfile

Returns a duplicate of the value.

fn clone_from(&mut self, source: &Self)

Performs copy-assignment from source.

impl Copy for GraphIoProfile

impl Debug for GraphIoProfile

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.

impl Default for GraphIoProfile

fn default() -> GraphIoProfile

Returns the “default value” for a type.

impl<'de> Deserialize<'de> for GraphIoProfile

fn deserialize<__D>(__deserializer: __D) -> Result<Self, __D::Error>

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl Eq for GraphIoProfile

impl PartialEq for GraphIoProfile

fn eq(&self, other: &GraphIoProfile) -> bool

Tests for self and other values to be equal, and is used by ==.

fn ne(&self, other: &Rhs) -> bool

Tests for !=. The default implementation is almost always sufficient, and should not be overridden without very good reason.

impl Serialize for GraphIoProfile

fn serialize<__S>(&self, __serializer: __S) -> Result<__S::Ok, __S::Error>

where __S: Serializer,

Serialize this value into the given Serde serializer.

impl StructuralPartialEq for GraphIoProfile